CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization Paper โข 2603.06449 โข Published 16 days ago โข 6
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm Paper โข 2511.04570 โข Published Nov 6, 2025 โข 242
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction Paper โข 2512.16900 โข Published Dec 18, 2025 โข 11
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion Paper โข 2512.04926 โข Published Dec 4, 2025 โข 42
StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation Paper โข 2508.08248 โข Published Aug 11, 2025 โข 27